Prisma ORM is a Node.js and TypeScript database toolkit that lets applications work with databases through a programming interface instead of writing every query directly in SQL. Developers use it with databases including PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB, and CockroachDB. The catalogue add-ons provide agent rules, skills, hooks, agents, and other workflows for using Prisma.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/prisma/orm/create-prnpx skills add prisma/orm --skill create-prgit clone --depth 1 https://github.com/prisma/ormWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/prisma/orm/create-pr)<a href="https://agentmods.dev/skills/prisma/orm/create-pr"><img src="https://agentmods.dev/badge/skills/prisma/orm/create-pr.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.04346 |
| Opus 5 | $0.00023 | $0.02173 |
| Sonnet 5 | $0.00009 | $0.00869 |
| Haiku 4.5 | $0.00005 | $0.00435 |
Grade A, and why
create-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR Skill
Instructions
Step 1: Gather Context
Detect the PR's base branch instead of hardcoding main. Set BASE_BRANCH once and reuse it in every diff/log command:
BASE_BRANCH=$(git rev-parse --abbrev-ref origin/HEAD 2>/dev/null | sed 's@^origin/@@')
BASE_BRANCH=${BASE_BRANCH:-main}
git rev-parse --abbrev-ref origin/HEAD returns the remote's default branch (e.g. origin/main); the sed strips the origin/ prefix. The fallback to main covers repos where origin/HEAD is unset. If you know the PR was branched off a non-default branch, override BASE_BRANCH explicitly before running the commands below.
- Run
git log "$BASE_BRANCH..HEAD" --onelineto see all commits on the current branch (fallback:git log "origin/$BASE_BRANCH..HEAD" --oneline). - Run
git diff "$BASE_BRANCH...HEAD" --statto see which files changed (fallback:git diff "origin/$BASE_BRANCH...HEAD" --stat). - Run
git diff "$BASE_BRANCH...HEAD"to read the full diff (fallback:git diff "origin/$BASE_BRANCH...HEAD"). - Check for local-only changes that won't be in the PR unless committed:
git status -sb- If there are uncommitted changes, explicitly call out that
gh pr createcan proceed but those changes will not be in the PR.
Step 2: Resolve the Linear Ticket
Resolve the Linear ticket from context — do not ask the user. The ticket is almost always derivable from one of:
- The branch name. Most branches are named
tml-NNNN-…(lower-case form of the Linear identifier). The current ticket is whatever matches(?i)\b(TML-\d+)\bingit rev-parse --abbrev-ref HEAD. Use the trailing slug from the branch name verbatim as$SLUG. - The conversation context. If the user previously linked or named a ticket in this conversation, use that.
- The most recent commit messages on the branch. Look for a
Refs: TML-NNNNor(TML-NNNN)trailer / mention ingit log "$BASE_BRANCH..HEAD".
Extract:
$TICKET_ID— the canonical upper-case identifier (e.g.,TML-1859)$SLUG— the trailing slug used in Linear URLs (e.g.,pn-add-more-parameterized-types); take it directly from the branch name's trailing portion when available
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 194 lines · 47 tokens per session scan A 3538af2968cd
create-pr is a skill published in the GitHub repository prisma/orm (47,601 stars, last pushed 2d ago), licensed Apache-2.0. It adds 47 tokens to every session and 4,346 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
multiline-commit-messages
Use single-quoted strings for multiline git commit messages in the Shell tool. Prevents heredoc escaping failures that produce garbled commit messages.
commit
Commit message formatting and guidelines.
commit
Create a git commit with optional automatic Linear issue linking. Use when the user asks to commit.
stacking-prs
Create and manage GitHub native Stacked PRs in this repo with the gh stack CLI. Use when asked to stack PRs, split a large change into a stack, add a layer to a stack, restack or rebase a stack, adopt existing branches or PRs into a stack, check out someone else's stack, or land a stack. Covers creating and submitting…
session-wrapup
End-of-session checkpoint — append diary, update active sprint doc with interim results/retro, write tech-lead handoff, commit and push. Use before /compact or at end-of-day. Distinct from sprint-wrap-up which closes a sprint.